Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    special characters and punctuation marks, particularly those related to dividing sections or indicating continuity in data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    spread out, sending follow-ups, responsible for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     [
    -0.33
     skall
    -0.32
    providedIn
    -0.32
     Selatan
    -0.31
    -0.31
     porcelana
    -0.30
     destes
    -0.30
     volna
    -0.29
     škole
    -0.29
     cuarenta
    -0.28
    POSITIVE LOGITS
     imagui
    0.84
     للمعارف
    0.82
    <unused79>
    0.82
    [@BOS@]
    0.82
    <unused52>
    0.82
    <unused28>
    0.81
    <unused41>
    0.81
    <unused17>
    0.81
    <unused3>
    0.81
    <unused8>
    0.81
    Act Density 0.000%

    No Known Activations